© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 55591
    Prev
    Next
    INDEX
    Explanations

    names of individuals and their affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Gong, Yang, Tu, Yu, Ho

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inig
    -0.42
     sav
    -0.38
     mix
    -0.37
     enc
    -0.37
    endregion
    -0.36
    توض
    -0.36
     craft
    -0.36
    Gur
    -0.35
     것
    -0.35
     equili
    -0.35
    POSITIVE LOGITS
    enumii
    0.61
    serviceWorker
    0.58
    ConstraintMaker
    0.57
    queryInterface
    0.57
     Chriftian
    0.56
    oa̍t
    0.55
     Chinois
    0.54
     himſelf
    0.53
     betweenstory
    0.52
     Cantonese
    0.51
    Activations Density 0.126%

    No Known Activations